Lum1104 — 8 Open-Source AI Agent Skills

Lum1104 is the author of 8 open-source AI agent skills and MCP servers spanning claude-skill, mcp-server, with a combined 49,955+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 51/100) and security-graded — 8 verified safe.

Top skills by Lum1104

• Understand-Anything — Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. (49.9k★ · quality 67/100 · security: safe)
• video-to-skill — Turn videos and courses into evidence-grounded Agent Skills for Claude Code and Codex. (18★ · quality 70/100 · security: safe)
• uni-code — Switch back and forth between Claude Code, Codex, and beyond — every agent's sessions in one searchable place, served to your agents over MC (4★ · quality 50/100 · security: safe)
• archaeologist — Your agents see old code. This skill makes them dig up why it exists. (2★ · quality 41/100 · security: safe)
• red-button — Your agents treat every change like a green light. This skill adds a red button for risky ones. (2★ · quality 48/100 · security: safe)
• prove-me-wrong — Your agents have a theory. This skill makes them ask, “What would prove me wrong?” (2★ · quality 44/100 · security: safe)
• bet-on-it — Your agents change the code, then explain why. This skill makes them bet on the result first. (2★ · quality 44/100 · security: safe)
• no-vibes — Your agents call it done on vibes. This skill makes them prove it. (2★ · quality 44/100 · security: safe)

View Lum1104 on GitHub · Explore audited agent skills